Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned
@article{Tranzatto2022TeamCW,
title={Team CERBERUS Wins the DARPA Subterranean Challenge: Technical Overview and Lessons Learned},
author={Marco Tranzatto and Mihir Dharmadhikari and Lukas Bernreiter and Marco Camurri and Shehryar Khattak and Frank Mascarich and Patrick Pfreundschuh and David Wisth and Samuel Zimmermann and Mihir Kulkarni and Victor Reijgwart and Benoit Casseau and Timon Homberger and Paolo De Petris and Lionel Ott and Wayne Tubby and Gabriel Waibel and Huan Nguyen and C{\'e}sar Cadena and Russell Buchanan and Lorenz Wellhausen and Nikhil Khedekar and Olov Andersson and LinTong Zhang and Takahiro Miki and Tung Dang and Mat{\'i}as Mattamala and Markus Montenegro and Konrad Meyer and Xiangyu Wu and Adrien Briod and Mark Wilfried Mueller and Maurice F. Fallon and Roland Y. Siegwart and Marco Hutter and Kostas Alexis},
journal={ArXiv},
year={2022},
volume={abs/2207.04914}
}This article presents the CERBERUS robotic system-of-systems, which won the DARPA Subterranean Challenge Final Event in 2021. The Subterranean Challenge was organized by DARPA with the vision to facilitate the novel technologies necessary to reliably explore diverse underground environments despite the grueling challenges they present for robotic autonomy. Due to their geometric complexity, degraded perceptual conditions combined with lack of GPS support, austere navigation conditions, and…
Figures and Tables from this paper
figure 1 
table 1 
figure 2 
table 2 
figure 3 
table 3 
figure 4 
table 4 
figure 5 
table 5 
figure 6 
figure 7 
figure 8 
figure 9 
figure 10 
figure 11 
figure 12 
figure 13 
figure 14 
figure 15 
figure 16 
figure 17 
figure 18 
figure 19 
figure 20 
figure 21 
figure 22 
figure 23 
figure 24 
figure 25 
figure 26 
figure 27 
figure 28 
figure 29 
figure 30 
figure 31 
figure 32 
figure 33 
figure 34
7 Citations
ArtPlanner: Robust Legged Robot Navigation in the Field
- Computer Science
- 2023
ArtPlanner, the navigation planner used by team CERBERUS during the Finals of the DARPA Subterranean Challenge, is presented and examined, based on a sampling-based method that determines valid poses with a reachability abstraction and uses learned foothold scores to restrict areas considered safe for stepping.
Resilient Terrain Navigation with a 5 DOF Metal Detector Drone
- GeologyArXiv
- 2022
Micro aerial vehicles (MAVs) hold the potential for performing autonomous and contactless land surveys for the detection of landmines and explosive remnants of war (ERW). Metal detectors are the…
LiDAR-guided object search and detection in Subterranean Environments
- Computer Science2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
- 2022
This work presents a method that utilizes the complementary nature of vision and depth sensors to leverage multi-modal information to aid object detection at longer distances by utilizing a Pan-Tilt-Zoom camera system to perform a directed search.
Walking in Narrow Spaces: Safety-critical Locomotion Control for Quadrupedal Robots with Duality-based Optimization
- MathematicsArXiv
- 2022
—This paper presents a safety-critical locomotion control framework for quadrupedal robots. Our goal is to enable quadrupedal robots to safely navigate in cluttered environments. To tackle this, we…
Collision-tolerant Aerial Robots: A Survey
- Computer ScienceArXiv
- 2022
The current state-of-the-art within the niche of collision-tolerant micro aerial vehicles and different design approaches identified in the literature are reviewed, as well as methods that have focused on autonomy functionalities that exploit collision resilience are presented.
Semantics-aware Exploration and Inspection Path Planning
- Computer ScienceArXiv
- 2023
Evaluated in extensive simulation studies and experimental results using a flying robot, the planner delivers efficient combined exploration and high-fidelity inspection planning that is focused on the semantics of interest.
Marsupial Walking-and-Flying Robotic Deployment for Collaborative Exploration of Unknown Environments
- Computer Science2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)
- 2022
This work contributes a marsupial robotic system-of-systems involving a legged and an aerial robot capable of collaborative mapping and exploration path planning that exploits the heterogeneous…
References
SHOWING 1-10 OF 84 REFERENCES
CERBERUS: Autonomous Legged and Aerial Robotic Exploration in the Tunnel and Urban Circuits of the DARPA Subterranean Challenge
- Computer ScienceField Robotics
- 2022
The CERBERUS system-of-systems is presented, as a unified strategy for subterranean exploration using legged and flying robots, and relies on ANYmal quadraped as primary robots, exploiting their endurance and ability to traverse challenging terrain.
DARPA Subterranean Challenge: Multi-robotic Exploration of Underground Environments
- Computer ScienceMESAS
- 2019
A description of the multi-robot heterogeneous exploration system of the CTU-CRAS team, which scored third place in the Tunnel Circuit round, surpassing the performance of all other non-DARPA-funded competitors.
Resilient and Modular Subterranean Exploration with a Team of Roving and Flying Robots
- Computer Science
- 2022
This work details its approach to artifact detection, pose estimation, coordination, planning, control, and autonomy, and discusses its performance in the tunnel, urban, and self-organized cave circuits of the DARPA Subterranean Challenge.
System for multi-robotic exploration of underground environments CTU-CRAS-NORLAB in the DARPA Subterranean Challenge
- Computer ScienceField Robotics
- 2022
A heterogeneous exploration robotic system of the CTU-CRAS-NORLAB team, which achieved the third rank at the SubT Tunnel and Urban Circuit rounds and surpassed the performance of all other non-DARPA-funded teams.
Multi-Agent Autonomy: Advancements and Challenges in Subterranean Exploration
- Computer ScienceField Robotics
- 2022
A range of lessons was learned, most importantly, that frequent and comprehensive field testing in representative environments is key to rapidly refining system performance.
NeBula: Quest for Robotic Autonomy in Challenging Environments; TEAM CoSTAR at the DARPA Subterranean Challenge
- Computer ScienceArXiv
- 2021
The paper introduces NeBula (Networked Belief-aware Perceptual Autonomy), an uncertainty-aware framework that aims at enabling resilient and modular autonomy solutions by performing reasoning and decision making in the belief space (space of probability distributions over the robot and world states).
Autonomous Teamed Exploration of Subterranean Environments using Legged and Aerial Robots
- Computer Science2022 International Conference on Robotics and Automation (ICRA)
- 2022
This work is structured around the synergy of an onboard exploration path planner that allows for resilient long-term autonomy, and a multi-robot coordination framework that enables navigation in environments with steep slopes, and diverse geometries.
ArtPlanner: Robust Legged Robot Navigation in the Field
- Computer Science
- 2023
ArtPlanner, the navigation planner used by team CERBERUS during the Finals of the DARPA Subterranean Challenge, is presented and examined, based on a sampling-based method that determines valid poses with a reachability abstraction and uses learned foothold scores to restrict areas considered safe for stepping.
RMF-Owl: A Collision-Tolerant Flying Robot for Autonomous Subterranean Exploration
- Computer Science2022 International Conference on Unmanned Aircraft Systems (ICUAS)
- 2022
RMF-Owl is a new collision-tolerant aerial robot tailored for resilient autonomous subterranean exploration with focus on collision tolerance, resilient autonomy with robust localization and mapping, alongside high-performance exploration path planning in confined, obstacle-filled and topologically complex underground environments.
Graph‐based subterranean exploration path planning using aerial and legged robots
- Computer ScienceJ. Field Robotics
- 2020
A novel graph‐based subterranean exploration path planning method that is attuned to key topological properties of subterranean settings, such as large‐scale tunnel‐like networks and complex multibranched topologies is proposed.